QQ聊天记录多角度分析Python实现

import jieba
import re
import jieba.analyse
import xlwt
from matplotlib import font_manager
import matplotlib as mpl
import matplotlib.pyplot as plt
from matplotlib.backends.backend_pdf import PdfPages

myfont = font_manager.FontProperties(fname='simhei.ttf')
mpl.rcParams['axes.unicode_minus'] = False

f = open("qk.txt", "r")  # 以追加的方式

message = f.readlines()
name1 = 'PuzzleX'#我的昵称
name1_message = []
name2 = '输入另一个人的昵称'
name2_message = []
name1_word_count = 0
name2_word_count = 0
name1_time = []
name2_time = []
wbk = xlwt.Workbook(encoding='ascii')
sheet = wbk.add_sheet("message")  # Excel单元格名字
word_lst = []
key_list = []
pat = re.compile(r'(\d{4}-\d{1,2}-\d{1,2})')
pdf = PdfPages(name1 + '与' + 'DEMO' + '聊天记录分析' + '.pdf')
for line in message:  # 1.txt是需要分词统计的文档
        try:
            item = line.strip('\n\r').split('\t')  # 制表格切分
            tags = jieba.analyse.extract_tags(item[0])  # jieba分词
            if pat.match(str(item[0])) and name1 in str(item[0]):
                name1_time.append(item)
            elif pat.match(str(item[0])) and name2 in str(item[0]):
                name2_time.append(item)
            if (len(tags) == 7 or 6) and name1 in tags:
                pass
            elif (len(tags) == 7 or 6) and name2 in tags:
                pass
            else:
                # print(tags)
                for t in tags:
                    word_lst.append(t)
        except:
            pass

#  print(word_lst)
word_dict = {}
with open("wordCount.txt", 'w') as wf2:  # 打开文件

    for item in word_lst:
        if item not in word_dict:  # 统计数量
            word_dict[item] = 1
        else:
            word_dict[item] += 1

    orderList = list(word_dict.values())
    orderList.sort(reverse=True)
    for i in range(len(orderList)):
        for key in word_dict:
            if word_dict[key] == orderList[i]:
                wf2.write(key + ' ' + str(word_dict[key]) + '\n')  # 写入txt文档
                key_list.append(key)
                word_dict[key] = 0

for i in range(len(key_list)):
    sheet.write(i, 1, label=orderList[i])
    sheet.write(i, 0, label=key_list[i])
wbk.save('message.xls')  # 保存为 wordCount.xls文件

for i in range(len(message)):
    if name1 in message[i]:
        name1_message.append(message[i+1])
        name1_word_count += len(message[i+1])
    if name2 in message[i]:
        name2_message.append(message[i+1])
        name2_word_count += len(message[i + 1])

name1_count = len(name1_message)
name2_count = len(name2_message)
name1_time_do = {'0':0, '1':0, '2': 0, '3': 0, '4': 0, '5': 0, '6': 0, '7': 0, '8': 0, '9': 0, '10': 0, '11': 0,
                 '12': 0, '13': 0, '14': 0, '15': 0,'16': 0, '17': 0, '18': 0, '19': 0, '20': 0, '21': 0, '22': 0, '23': 0, }
name2_time_do = {'0':0, '1':0, '2': 0, '3': 0, '4': 0, '5': 0, '6': 0, '7': 0, '8': 0, '9': 0, '10': 0, '11': 0,
                 '12': 0, '13': 0, '14': 0, '15': 0, '16': 0, '17': 0, '18': 0, '19': 0, '20': 0, '21': 0, '22': 0, '23': 0, }

for item in name1_time:
    try:
        name1_time_do[str(item[0])[11:13]] += 1
    except KeyError:
        name1_time_do[str(item[0])[11:12]] += 1
for item in name2_time:
    try:
        name2_time_do[str(item[0])[11:13]] += 1
    except KeyError:
        name2_time_do[str(item[0])[11:12]] += 1

time_range = name1_time[0][0][:11] + '到' + name1_time[-1][0][:11]

plt.figure()
plt.axis('off')
t = name1 + '与' + 'DEMO' + '的聊天记录分析' + '\nomegaxyz.com\n\n' + name1 + '的消息发送次数为： ' + str(name1_count) + '\n' + 'DEMO' + \
    '的消息发送次数为： ' + str(name2_count) + '\n' + name1 + '的消息发送消息字数为： ' + str(name1_word_count) + '\n' + 'DEMO' + \
    '的消息发送消息字数为： ' + str(name2_word_count) + '\n\n' + time_range + '\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n'
plt.text(0, 0, t, ha='left', wrap=True, fontproperties=myfont)
pdf.savefig()
plt.close()

word_T1 = ' 聊天词频分析\n'
for i in range(25):
    word_T1 += key_list[i]
    word_T1 += '：'
    word_T1 += str(orderList[i]) + '\n'
plt.figure()
plt.axis('off')
plt.text(0, 0, word_T1, ha='left', wrap=True, fontproperties=myfont)
pdf.savefig()
plt.close()

word_T2 = ''
for i in range(25):
    word_T2 += key_list[i+25]
    word_T2 += '：'
    word_T2 += str(orderList[i+25]) + '\n'
plt.figure()
plt.axis('off')
plt.text(0, 0, word_T2, ha='left', wrap=True, fontproperties=myfont)
pdf.savefig()
plt.close()


# print(orderList[0:10])
# print(key_list[0:10])
rects = plt.bar(range(len(orderList[0:11])), orderList[0:11], color='rgby')
# X轴标题
index = [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
plt.ylim(ymax=orderList[0]*1.1, ymin=0)
plt.xticks(index, key_list[0:11], fontproperties=myfont)
plt.ylabel("次数", fontproperties=myfont)  # X轴标签
plt.title('聊天最多的词（包括表情和图片）', fontproperties=myfont)

for rect in rects:
    height = rect.get_height()
    plt.text(rect.get_x() + rect.get_width() / 2, height, str(height), ha='center', va='bottom')
plt.savefig('Top10 words.jpg')
pdf.savefig()
# plt.show()
plt.close()

plt.axis([0, 23, 0, 600])
plt.ion()
# print(list(name1_time_do))
plt.plot(list(name1_time_do), list(name1_time_do.values()), color='red', label='User1')
plt.plot(list(name2_time_do), list(name2_time_do.values()), color='blue', label='User2')
plt.xlabel('时间（24小时制）', fontproperties=myfont)
plt.ylabel('频率', fontproperties=myfont)
plt.title('聊天时间分布', fontproperties=myfont)
plt.savefig('time frequency.jpg')
pdf.savefig()
# plt.show()
plt.close()

pdf.close()